© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9944
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific and technical contexts, specifically referencing processes, examples, and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    This neuron activates for commas following a geographic location, mathematical expression, or technical term, particularly at the end of a clause or statement.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    commas and punctuation marks that separate clauses or list items.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arschijnlijk
    -0.46
    XtraBars
    -0.43
    soever
    -0.42
     arşivlendi
    -0.38
    amazonaws
    -0.37
    씩
    -0.36
    "}")
    -0.35
    LabelTagHelper
    -0.35
    IALE
    -0.35
    ysacchar
    -0.35
    POSITIVE LOGITS
     where
    3.69
    where
    2.92
     donde
    2.80
     où
    2.53
     где
    2.47
     gdzie
    2.36
     Where
    2.30
     wherein
    2.28
    Where
    2.27
     hvor
    2.22
    Activations Density 2.977%

    No Known Activations